Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Dec 11, 2025

Design and Analysis for Fall Detection System Simplification

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

Pre-Impact Fall Detection with CNN-Based Class Activation Mapping Method.

Jingyi Shi¹, Diansheng Chen^1,2, Min Wang³

¹Institute of Robotics, School of Mechanical Engineering and Automation, Beihang University, Beijing 100191, China.

Sensors (Basel, Switzerland)

|August 27, 2020

Summary

This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Evaluation of thermal camera measurement stability and factors associated with infrared eye temperature in dogs.

Frontiers in veterinary science·2026

Same author

Concurrent Alcohol Use and Smoking Among US Adults with Hepatitis C.

Journal of dual diagnosis·2026

Same author

PIP<sub>2</sub> activation of the cardiac I<sub>Ks</sub> potassium channel.

Nature communications·2026

Same author

Virus-immune signatures reveal distinct clinical phenotypes and predict prognosis in patients with Kaposi's sarcoma.

Journal of translational medicine·2026

Same author

Extracellular vesicles derived from TNF-α-preconditioned mesenchymal stem cells mitigate inflammatory retinal injury.

Extracellular vesicles and circulating nucleic acids·2026

Same author

Soft tissue and dentoskeletal changes associated with mandibular molar distalization using clear aligner therapy: a retrospective cross-sectional CBCT study.

Scientific reports·2026

Same journal

RETRACTED: Zhang et al. A Novel Framework for Reconstruction and Imaging of Target Scattering Centers via Wide-Angle Incidence in Radar Networks. <i>Sensors</i> 2025, <i>25</i>, 6802.

Sensors (Basel, Switzerland)·2026

Same journal

Enhancing Unsupervised Multi-Source Domain Adaptation for Person Re-Identification via Mixture of Experts and Graph-Based Relation.

Sensors (Basel, Switzerland)·2026

Same journal

Development of an Instrumented Glove for Palmar Pressure Assessment in Kayakers.

Sensors (Basel, Switzerland)·2026

Same journal

Development and Experimental Validation of an Autonomous IoT-Based Monitoring System for Real-Time Water Quality Assessment in the Amazon River.

Sensors (Basel, Switzerland)·2026

Same journal

Semi-Supervised Adversarial Learning Framework for Controller Area Network Bus Intrusion Detection.

Sensors (Basel, Switzerland)·2026

Same journal

Smart Optimization Method for Safety Signs in Innovative Manufacturing Environments Integrating Industrial Field IoT Sensors and Knowledge Graphs.

Sensors (Basel, Switzerland)·2026

See all related articles

This study enhances pre-impact fall detection using a learning-based method with inertial measurement unit (IMU) sensor data. The novel approach achieves high accuracy on wearable devices, improving fall prediction for individuals.

Area of Science:

Biomedical Engineering
Machine Learning for Healthcare
Wearable Sensor Technology

Background:

Traditional fall detection methods using fixed thresholds struggle with individual movement variations.
High-accuracy machine learning methods often require significant hardware, limiting wearable applications.
This research addresses the need for accurate, low-resource fall detection in wearable systems.

Discussion:

A hybrid approach combines machine learning with a novel thresholding technique derived from convolutional neural network (CNN) class activation mapping (CAM).
CAM identifies critical data regions for fall prediction, enabling feature extraction for a specialized threshold method.
This technique overcomes limitations of purely threshold-based or high-resource machine learning methods.

Key Insights:

Keywords:

IMU fall detection neural network pre-impact threshold-based

More Related Videos

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

Related Experiment Videos

Last Updated: Dec 11, 2025

Design and Analysis for Fall Detection System Simplification

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

The developed CNN-CAM model achieved 95.55% accuracy on the MobiAct dataset.
Manually extracted features from CAM-identified regions led to a specialized threshold method.
The hybrid method demonstrated 95.33% accuracy with a detection time under 400 ms for real-world fall prediction.

Outlook:

Potential for real-time, accurate fall prediction in diverse wearable health monitoring applications.
Further refinement of feature extraction and CNN architectures could enhance robustness.
Integration into elder care and rehabilitation monitoring systems is a promising future direction.